Search Results for author:
Found 31 papers, 28 papers with code
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
Interpretable machine learning: definitions, methods, and applications
Official code for using / reproducing ACD (ICLR 2019) from the paper "Hierarchical interpretations for neural network predictions" https://arxiv. org/abs/1806. 05337
Fast Interpretable Greedy-Tree Sums
In such settings, practitioners often use highly interpretable decision tree models, but these suffer from inductive bias against additive structure.
Hierarchical Shrinkage: improving the accuracy and interpretability of tree-based methods
Tree-based models such as decision trees and random forests (RF) are a cornerstone of modern machine-learning practice.
NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation
Data augmentation is an important component in the robustness evaluation of models in natural language processing (NLP) and in enhancing the diversity of the data they are trained on.
Curating a COVID-19 data repository and forecasting county-level death counts in the United States
We use this data to develop predictions and corresponding prediction intervals for the short-term trajectory of COVID-19 cumulative death counts at the county-level in the United States up to two weeks ahead.
Disentangled Attribution Curves for Interpreting Random Forests and Boosted Trees
Tree ensembles, such as random forests and AdaBoost, are ubiquitous machine learning models known for achieving strong predictive performance across a wide variety of domains.
Interpretations are useful: penalizing explanations to align neural networks with prior knowledge
For an explanation of a deep learning model to be effective, it must provide both insight into a model and suggest a corresponding action in order to achieve some objective.
Interpreting and improving deep-learning models with reality checks
Recent deep-learning models have achieved impressive predictive performance by learning complex functions of many variables, often at the cost of interpretability.
Hierarchical interpretations for neural network predictions
Deep neural networks (DNNs) have achieved impressive predictive performance due to their ability to learn complex, non-linear relationships between variables.
Learning a Decision Tree Algorithm with Transformers
We then train MetaTree to produce the trees that achieve strong generalization performance.
Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs
In human-written articles, we often leverage the subtleties of text style, such as bold and italics, to guide the attention of readers.
Augmenting Interpretable Models with LLMs during Training
Recent large language models (LLMs) have demonstrated remarkable prediction performance for a growing array of tasks.
Explaining Patterns in Data with Language Models via Interpretable Autoprompting
Large language models (LLMs) have displayed an impressive ability to harness natural language to perform complex tasks.
Explaining black box text modules in natural language with language models
Here, we ask whether we can automatically obtain natural language explanations for black box text modules.
Rethinking Interpretability in the Era of Large Language Models
We highlight two emerging research priorities for LLM interpretation: using LLMs to directly analyze new datasets and to generate interactive explanations.
Adaptive wavelet distillation from neural networks through interpretations
Moreover, interpretable models are concise and often yield computational efficiency.
Self-Verification Improves Few-Shot Clinical Information Extraction
Extracting patient information from unstructured text is a critical task in health decision-support and clinical research.
Tree Prompting: Efficient Task Adaptation without Fine-Tuning
Prompting language models (LMs) is the main interface for applying them to new tasks.
Matched sample selection with GANs for mitigating attribute confounding
Measuring biases of vision systems with respect to protected attributes like gender and age is critical as these systems gain widespread use in society.
Revisiting minimum description length complexity in overparameterized models
We provide an extensive theoretical characterization of MDL-COMP for linear models and kernel methods and show that it is not just a function of parameter count, but rather a function of the singular values of the design or the kernel matrix and the signal-to-noise ratio.
Group Probability-Weighted Tree Sums for Interpretable Modeling of Heterogeneous Data
Machine learning in high-stakes domains, such as healthcare, faces two critical challenges: (1) generalizing to diverse data distributions given limited training data while (2) maintaining interpretability.
Large Scale Image Segmentation with Structured Loss based Deep Learning for Connectome Reconstruction
Our extension consists of two parts: First, we present a quasi-linear method to compute the loss gradient, improving over the original quadratic algorithm.
Ranked #1 on
Brain Image Segmentation
on FIB-25 Synaptic Sites
Transformation Importance with Applications to Cosmology
Machine learning lies at the heart of new possibilities for scientific discovery, knowledge generation, and artificial intelligence.
A Constrained, Weighted-L1 Minimization Approach for Joint Discovery of Heterogeneous Neural Connectivity Graphs
Determining functional brain connectivity is crucial to understanding the brain and neural differences underlying disorders such as autism.
Attribute Structuring Improves LLM-Based Evaluation of Clinical Text Summaries
Summarizing clinical text is crucial in health decision-support and clinical research.
Learning Invariant Representations for Equivariant Neural Networks Using Orthogonal Moments
The final classification layer in equivariant neural networks is invariant to different affine geometric transformations such as rotation, reflection and translation, and the scalar value is obtained by either eliminating the spatial dimensions of filter responses using convolution and down-sampling throughout the network or average is taken over the filter responses.
Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning
We propose explanation-consistency finetuning (EC-finetuning), a method that adapts LLMs to generate more consistent natural-language explanations on related examples.
A consensus layer v pyramidal neuron can sustain interpulse-interval coding
As a proxy for an IPI, a neuron’s time-to-spike can be found in the biophysical and experimental intracellular literature.
Linearization of excitatory synaptic integration at no extra cost
In many theories of neural computation, linearly summed synaptic activation is a pervasive assumption for the computations performed by individual neurons.
Complexity Leads to Simplicity: A Consensus Layer V Pyramidal Neuron Can Sustain Interpulse-Interval Coding
In terms of the long-distance communication of a single neuron, interpulse intervals (IPIs) are a possible alternative to rate and binary codes.
Neurons and Cognition
